An Exploratory Study of Students’ Learning Performance In Flipped Classroom Using Decision Tree and Regression

Abstract

Flipped Classroom model is one of the most effective and influential approaches that follow a student-centered approach. It may enhance students’ learning skills and creates a motivational level by conducting learning activities in pre-class and post-class sessions. The main purpose of this research is to demonstrate how a combined, teaching and machine learning approach can be useful in evaluating student learning outcomes by analyzing their learning performance. Furthermore, this can help the instructor to counsel students whose performance is lagging during the semester. To perform predictive analysis and classification, we have implemented linear regression and decision tree classifier that helps the instructor to predict and classify students learning outcomes based on their overall performance before final exams.